tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- output:
url: images/8c013c0c-7de1-4ad5-b9c3-5af5b5c965f8.png
text: masterpiece, best quality, blurry, bloom
parameters:
negative_prompt: >-
text, long body, lowres, cropped, lowres, jpeg artifacts, (signature,
artist name, watermark, username, english text, signature:1.4), simple
background, conjoined, out of frame, out of frame, censored, bar censor,
cameltoe,
base_model: calcuis/illustrious
instance_prompt: domi-h2o
Domi Style - Illustrious
- Prompt
- masterpiece, best quality, blurry, bloom
- Negative Prompt
- text, long body, lowres, cropped, lowres, jpeg artifacts, (signature, artist name, watermark, username, english text, signature:1.4), simple background, conjoined, out of frame, out of frame, censored, bar censor, cameltoe,
Model description
The style of Domi.
I made this lora to try and reproduce the style of Domi (hongsung0819).
Illustrious V2
I remade this version, because it was made based on pony lora creation settings. Because of this some things have changed.
For the quality tags I used the following: masterpiece, best quality, blurry, bloom (I added blurry and bloom to try to capture the effect of the original art, so they are not mandatory)
For the negatives I used the following in general: text, long body, lowres, cropped, lowres, jpeg artifacts, (signature, artist name, watermark, username, english text, signature:1.4), simple background, conjoined, out of frame, out of frame, censored, bar censor,
I used ADetailer plugin with the a face model to improve the quality, but this is not mandatory to get good results..
The Trigger is: domi-h2o,
Advised strength: 0.6-1.0
Trigger words
You should use domi-h2o to trigger the image generation.
Download model
Download them in the Files & versions tab.